Redistribution effects of water tariffs

Nguyen Bich Ngoc, Jacques Teller 13 December 2021

inccatdf <- df[!(is.na(df$inccat)),] %>%
  group_by(inccat) %>%
  summarise(count = n(),
            prop = n()/nrow(df),
            income_avr = mean(income),
            income_min = min(income),
            income_max = max(income),
            inceqa_avr = mean(inceqa),
            inceqa_min = min(inceqa),
            inceqa_max = max(inceqa))

inccatdf

## # A tibble: 4 x 9
##   inccat     count   prop income_avr income_min income_max inceqa_avr
##   <fct>      <int>  <dbl>      <dbl>      <int>      <int>      <dbl>
## 1 precarious   148 0.0970      1135.        125       2250      8854.
## 2 modest       697 0.457       1881.       1250       3250     15961.
## 3 average      501 0.329       3203.       2250       4750     23622.
## 4 higher       178 0.117       4739.       3750       5250     30957.
## # ... with 2 more variables: inceqa_min <dbl>, inceqa_max <dbl>

## Warning: Removed 192 row(s) containing missing values (geom_path).

## Warning: Removed 150 row(s) containing missing values (geom_path).

# Correlation between water consumption and household income should use spearman?????

cor.test(df$csmptv, df$income, method = "pearson")

## 
##  Pearson's product-moment correlation
## 
## data:  df$csmptv and df$income
## t = 15.505, df = 1523, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.3250574 0.4117940
## sample estimates:
##       cor 
## 0.3692295

cor.test(df$csmptv, df$income, method = "spearman")

## Warning in cor.test.default(df$csmptv, df$income, method = "spearman"):
## Cannot compute exact p-value with ties

## 
##  Spearman's rank correlation rho
## 
## data:  df$csmptv and df$income
## S = 358665135, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.3932203

# Correlation between water consumption and income per equivalent adult should use spearman?????

cor.test(df$csmptv, df$inceqa, method = "pearson")

## 
##  Pearson's product-moment correlation
## 
## data:  df$csmptv and df$inceqa
## t = 1.8473, df = 1523, p-value = 0.06489
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.00291998  0.09724963
## sample estimates:
##       cor 
## 0.0472837

cor.test(df$csmptv, df$inceqa, method = "spearman")

## Warning in cor.test.default(df$csmptv, df$inceqa, method = "spearman"):
## Cannot compute exact p-value with ties

## 
##  Spearman's rank correlation rho
## 
## data:  df$csmptv and df$inceqa
## S = 547594684, p-value = 0.004034
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## 0.07359449

## Warning: Removed 9 rows containing non-finite values (stat_boxplot).

## Warning: Removed 9 rows containing non-finite values (stat_summary).

## Warning: Removed 9 rows containing non-finite values (stat_summary).

## Warning: Removed 9 rows containing non-finite values (stat_boxplot).

## Warning: Removed 9 rows containing non-finite values (stat_summary).

## Warning: Removed 9 rows containing non-finite values (stat_summary).

summary(df$avrprc)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   3.955   4.324   4.419   4.910   4.576  20.055

summary(df$avrprc[df$poorest == 1])

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   4.076   4.416   4.551   5.606   5.499  16.277

summary(df$avrprc[df$inccat == "precarious"])

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   3.971   4.332   4.457   5.098   4.665  16.277       1

summary(df$subs[df$inccat == "precarious"])

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
## -79.564  -4.286   1.840  -3.918  10.142  30.484       1

summary(df$mgnprc)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.080   4.193   4.193   3.693   4.193   4.382

summary(df$mgnprc[df$poorest == 1])

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.080   1.224   4.193   3.155   4.193   4.382

summary(df$mgnprc[df$inccat == "precarious"])

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   1.080   3.905   4.193   3.478   4.193   4.382       1

## 3.5. changing fixed  -----

### new cvd ------